> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Integrate a custom AI model in an application

> Choose the right Qualcomm SDK path to deploy a custom AI model in an application, using the Qualcomm IM SDK or the Qualcomm AI Runtime SDK.

This section describes the available paths for deploying a custom model using Qualcomm SDKs.

To use a custom model in an AI application, you can use the Qualcomm Intelligent Multimedia SDK or Qualcomm AI Runtime SDK.

<Frame caption="**Bring your own model: Time taken to deploy a model**">
  <img src="https://mintcdn.com/qualcomm-prod/L-jqwrTTz49ZAgVX/Key-Documents/AI-Developer-Workflow/_images/integrate-custom-model-in-app.png?fit=max&auto=format&n=L-jqwrTTz49ZAgVX&q=85&s=2bb31c0134f1eaf4866ed5a5b64f314f" alt="**Bring your own model: Time taken to deploy a model**" width="1054" height="687" data-path="Key-Documents/AI-Developer-Workflow/_images/integrate-custom-model-in-app.png" />
</Frame>

**Using Qualcomm IM SDK**

| SDK supported use case? | SDK supported model? | Number of AI Hub models available | Expected time to integrate the model in an application |
| ----------------------- | -------------------- | --------------------------------- | ------------------------------------------------------ |
| Yes                     | Yes                  | 84                                | 15 minutes<br />This is an advanced use case.          |

**Using Qualcomm AI Runtime SDK**

| SDK supported use case? | SDK supported model? | Number of AI Hub models available | Expected time to integrate the model in an application |
| ----------------------- | -------------------- | --------------------------------- | ------------------------------------------------------ |
| No constraints          | No constraints       | NA                                | \~1 week<br />This is an advanced use case.            |

<Note>
  The moderate and advanced paths assume understanding of
  [GStreamer fundamentals](https://gstreamer.freedesktop.org/documentation/tutorials/index.html),
  understanding of [GStreamer pipelines](https://gstreamer.freedesktop.org/documentation/gstreamer/gstpipeline.html?gi-language=c),
  expertise in C/C++, and a [Yocto build environment](https://docs.yoctoproject.org/brief-yoctoprojectqs/index.html).
</Note>